Technique Updated 2026-04

Function Calling

Definition

Function Calling enables an LLM to call external functions or APIs in a structured way to execute concrete actions.

See also in the glossary

A
AI Agent
An AI agent is an autonomous system that uses an LLM to plan, decide and execute real tasks without human intervention at each step.
A
AI API
An AI API allows developers to integrate artificial intelligence capabilities into their applications.
M
MCP (Model Context Protocol)
MCP is an open protocol that standardizes the connection between LLMs and external tools/data.
S
Structured Output
Structured Output forces an LLM to respond in a predefined structured format (JSON, XML, table) instead of free text.

Tools that use function calling

C
ChatGPT
The world's most used conversational AI assistant
4.6/5
C
Claude
The AI that understands nuance, by Anthropic
4.7/5
G
Gemini
Google's AI assistant with 1M token context
4.5/5
O
OpenClaw
The open source AI agent that turns your LLMs into autonomous workers
4.5/5

Frequently Asked Questions

Are Function Calling and MCP the same?
No but related. Function Calling is the LLM's ability to call functions. MCP is a protocol that standardizes which functions are available and how to call them.
Do all LLMs support Function Calling?
The major ones do: GPT-4o, Claude, Gemini, Mistral. It's the technical foundation for AI agents that interact with external tools.